The 15th Web for All Conference Lyon, France 2018

Keynote

A Person Like Me:Virtual Peers as Interface and Education

Justine Cassell, Carnegie Mellon University, USA

Students learn more when they study with friends than with strangers. Patients who feel respected by their doctors are more likely to enroll in medical trials. Sometimes you just need somebody like you - or even who just likes you - to help you succeed. In this talk I'll describe how we build this same experience - of working with somebody like you - into technology. Applications include peer tutoring of linear algebra, scaffolding social skills in individuals with Aspergers, teaching science to children who speak non-mainstream dialects, and virtual personal assistants who really get what their human bosses are looking for. Each step of the talk is illustrated by experiments that involve human-human and human-virtual human interaction. I include novel approaches to modeling and generating behaviors for human-computer interaction on the basis of human-human corpora. And finally, lessons are drawn both for the understanding of human behavior, and the improved design of technologies capable of engaging in satisfying relationships and more effective interactions with people over the long-term.

Notes:

Session 8: Internet of Things - 2 of 2

Home Automation for an Independent Living: Investigating Needs of the Visually Impaired People

Barbara Leporini, Marina Buzzi, ISTI-CNR

Independence is essential for anyone and crucial for people with disabilities. Being able to perform daily actions as much as possible autonomously is an important step towards a real inclusion and an independent life. Several technology-enhanced services and tools are steadily proposed to the special-need users, but are they really used and appreciated by them? New technology and sensors are increasingly used to develop solutions aimed at improving the quality of life for all, including people with vision impairments. Smart home is an example going into this direction. This paper collects blind users’ expectations and habits regarding technology for home automation through an online survey and some interviews. Specifically forty-two visually impaired people answered to an accessible online questionnaire shedding light on their needs and preferences. Next some semi-structured short interviews conducted with a group of eight thoroughly blind participants have enabled the collection of relevant user requirements useful for better understanding some aspects of experienced obstacles, and for designing usable functions of home automation and remote control systems. Results showed that main requests are for gaining autonomy in every day tasks and having more usability and flexibility in using remote control and home automation systems. Thanks to the collected feedback a set of general suggestions for designers and developers of home automation systems and devices has been proposed in order to enhances their accessibility and usability.

Notes:

Session 9: Learning Disabilities

Detecting Autism Based on Eye-Tracking Data from Web Searching Tasks

Victoria Yaneva, Le An Ha, Ruslan Mitkov, University of Wolverhampton; Sukru Eraslan, Yeliz Yesilada, Middle East Technical University

The ASD diagnosis requires a long, elaborate, and expensive procedure, which is subjective and is currently restricted to behavioural, historical, and parent-report information. In this paper, we present an alternative way for detecting the condition based on the atypical visual-attention patterns of people with autism. We collect gaze data from two different kinds of tasks related to processing of information from web pages: Browsing and Searching. The gaze data is then used to train a machine learning classifier whose aim is to distinguish between participants with autism and a control group of participants without autism. In addition, we explore the effects of the type of the task performed, different approaches to defining the areas of interest, gender, visual complexity of the web pages and whether or not an area of interest contained the correct answer to a searching task.

Our best-performing classifier achieved 0.75 classification accuracy for a combination of selected web pages using all gaze features. These preliminary results show that the differences in the way people with autism process web content could be used for the future development of serious games for autism screening. The gaze data, R code, visual stimuli and task descriptions are made freely available for replication purposes.

Notes:

Towards a Language Independent Detection of Dyslexia with a Web-Game

Maria Rauschenberger, Ricardo Baeza-Yates, Universitat Pompeu Fabra; Luz Rello, Jeffrey P. Bigham, Carnegie Mellon University

Detecting dyslexia is important because early intervention is key to avoid the negative effects of dyslexia such as school failure. Most of the current approaches to detect dyslexia require expensive personnel (i.e. psychologists) or special hardware (i.e. eye trackers or MRI machines). Also, most of the methods can only be used when children are learning how to read but not before, necessarily delaying needed early intervention. In this paper, we present a study with 178 participants speaking different languages (Spanish, German, English, and Catalan) with and without dyslexia using a game build with language independent content: musical and visual elements. The study reveals eighth game measures with significant differences for children with and without dyslexia, which could be used in future work as a basis for language independent detection.

Notes:

Computer Anxiety and Interaction: A Systematic Review

Thiago Donizetti dos Santos, Federal University of ABC; Vagner Figueredo de Santana, IBM Research

With the increasing use of technology in everyday life, one would expect that the use of computers would be comfortable and straightforward for everyone. However, some people still feel intimidated when using computers.

Those people face multiple levels of anxiety and, for high levels, demonstrate what is called Computer Anxiety. People with Computer Anxiety (PwCA) face problems when using computers/technology at home, in the workplace, or for study purposes, which might result in multiple forms of barriers.

This work contributes with a systematic review, summarizing the main approaches related to Computer Anxiety and the understanding of the contexts of use involving PwCA.

The main results are that Computer Anxiety Rating Scale (CARS) is the most popular scale for measuring Computer Anxiety, Computer Self-Efficacy has a negative strong relationship with Computer Anxiety, experience in using computers reduce Computer Anxiety, PwCA tend to take more time to complete tasks, and that higher education levels are related with lower levels of Computer Anxiety.

The results obtained are valuable for researchers working on identifying and removing barriers in systems aiming at the population of older adults, given that they are greatly impacted by Computer Anxiety in the context of technology adoption.

Notes:

Automatic Natural Language Generation Applied to Alternative and Augmentative Communication for Online Video Content Services using SimpleNLG for Spanish

Silvia García-Méndez, Milagros Fernández-Gavilanes, Enrique Costa-Montenegro, Jonathan Juncal-Martínez, Francisco Javier González-Castaño, GTI Research Group, atlanTTic

We present our work to build the Spanish version of SimpleNLG, the Natural Language Generation library, by adapting the existing free version of the library and creating new code to satisfy the linguistic requirements of Spanish. Not only have we developed a Spanish version of SimpleNLG, but also we have achieved a library that only needs the main words as input and it is able to conduct the generation process on its own, taking care of syntax structures and morphology inflections, among other linguistic considerations. The adaptation of the library uses aLexiS, a complete and reliable lexicon with morphology that we created. On the other hand, the enhanced version of SimpleNLG uses Elsa: the Augmentative Spanish Lexicon created from the pictogram domain, containing not only morphological data (as aLexiS) but also syntactic and semantic information needed to conduct the generation process automatically. Both the adaptation of SimpleNLG to Spanish and its enhanced version may be useful integrated in several applications as well as web applications, bringing them natural language generation functionalities. We provide a use case of the system focused on Augmentative and Alternative Communication and online video content services.

Notes:

Artificial Intelligence for Web Accessibility - Conformance Evaluation as a Way Forward?

Shadi Abou-Zahra, Judy Brewer, Michael Cooper, W3C Web Accessibility Initiative (WAI)

The term “artificial intelligence” is a buzzword today and is heavily used to market products, services, research, conferences, and more. It is scientifically disputed which types of products and services do actually qualify as “artificial intelligence” versus simply advanced computer technologies mimicking aspects of natural intelligence.

Yet it is undisputed that, despite often inflationary use of the term, there are mainstream products and services today that for decades were only thought to be science fiction. They range from industrial automation, to self-driving cars, robotics, and consumer electronics for smart homes, workspaces, education, and many more contexts.

Several technological advances enable what is commonly referred to as “artificial intelligence”. It includes connected computers and the Internet of Things (IoT), open and big data, low cost computing and storage, and many more. Yet regardless of the definition of the term artificial intelligence, technological advancements in this area provide immense potential, especially for people with disabilities.

In this paper we explore some of these potential in the context of web accessibility. We review some existing products and services, and their support for web accessibility. We propose accessibility conformance evaluation as one potential way forward, to accelerate the uptake of artificial intelligence to improve web accessibility.
Notes: